Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications

AI agents powered by large language models (LLMs) have shown strong capabilities in problem solving. Through combining many intelligent agents, multi-agent collaboration has emerged as a promising approach to tackle complex, multi-faceted problems that exceed the capabilities of single AI agents. However, designing the collaboration protocols and evaluating the effectiveness of these systems remains a significant challenge, especially for enterprise applications. This report addresses these challenges by presenting a comprehensive evaluation of coordination and routing capabilities in a novel multi-agent collaboration framework. We evaluate two key operational modes: (1) a coordination mode enabling complex task completion through parallel communication and payload referencing, and (2) a routing mode for efficient message forwarding between agents. We benchmark on a set of handcrafted scenarios from three enterprise domains, which are publicly released with the report. For coordination capabilities, we demonstrate the effectiveness of inter-agent communication and payload referencing mechanisms, achieving end-to-end goal success rates of 90%. Our analysis yields several key findings: multi-agent collaboration enhances goal success rates by up to 70% compared to single-agent approaches in our benchmarks; payload referencing improves performance on code-intensive tasks by 23%; latency can be substantially reduced with a routing mechanism that selectively bypasses agent orchestration. These findings offer valuable guidance for enterprise deployments of multi-agent systems and advance the development of scalable, efficient multi-agent collaboration frameworks.

MegaWika: Millions of reports and their sources across 50 diverse languages

To foster the development of new models for collaborative AI-assisted report generation, we introduce MegaWika, consisting of 13 million Wikipedia articles in 50 diverse languages, along with their 71 million referenced source materials. We process this dataset for a myriad of applications, going beyond the initial Wikipedia citation extraction and web scraping of content, including translating non-English articles for cross-lingual applications and providing FrameNet parses for automated semantic analysis. MegaWika is the largest resource for sentence-level report generation and the only report generation dataset that is multilingual. We manually analyze the quality of this resource through a semantically stratified sample. Finally, we provide baseline results and trained models for crucial steps in automated report generation: cross-lingual question answering and citation retrieval.

InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction

Learning template based information extraction from documents is a crucial yet difficult task. Prior template-based IE approaches assume foreknowledge of the domain templates; however, real-world IE do not have pre-defined schemas and it is a figure-out-as you go phenomena. To quickly bootstrap templates in a real-world setting, we need to induce template slots from documents with zero or minimal supervision. Since the purpose of question answering intersect with the goal of information extraction, we use automatic question generation to induce template slots from the documents and investigate how a tiny amount of a proxy human-supervision on-the-fly (termed as InteractiveIE) can further boost the performance. Extensive experiments on biomedical and legal documents, where obtaining training data is expensive, reveal encouraging trends of performance improvement using InteractiveIE over AI-only baseline.

Adaptive Active Learning for Coreference Resolution

Training coreference resolution models require comprehensively labeled data. A model trained on one dataset may not successfully transfer to new domains. This paper investigates an approach to active learning for coreference resolution that feeds discrete annotations to an incremental clustering model. The recent developments in incremental coreference resolution allow for a novel approach to active learning in this setting. Through this new framework, we analyze important factors in data acquisition, like sources of model uncertainty and balancing reading and labeling costs. We explore different settings through simulated labeling with gold data. By lowering the data barrier for coreference, coreference resolvers can rapidly adapt to a series of previously unconsidered domains.

Cold-start Active Learning through Self-supervised Language Modeling

Active learning strives to reduce annotation costs by choosing the most critical examples to label. Typically, the active learning strategy is contingent on the classification model. For instance, uncertainty sampling depends on poorly calibrated model confidence scores. In the cold-start setting, active learning is impractical because of model instability and data scarcity. Fortunately, modern NLP provides an additional source of information: pre-trained language models. The pre-training loss can find examples that surprise the model and should be labeled for efficient fine-tuning. Therefore, we treat the language modeling loss as a proxy for classification uncertainty. With BERT, we develop a simple strategy based on the masked language modeling loss that minimizes labeling costs for text classification. Compared to other baselines, our approach reaches higher accuracy within less sampling iterations and computation time.

Interactive Refinement of Cross-Lingual Word Embeddings

Cross-lingual word embeddings transfer knowledge between languages: models trained for a high-resource language can be used in a low-resource language. These embeddings are usually trained on general-purpose corpora but used for a domain-specific task. We introduce CLIME, an interactive system that allows a user to quickly adapt cross-lingual word embeddings for a given classification problem. First, words in the vocabulary are ranked by their salience to the downstream task. Then, salient keywords are displayed on an interface. Users mark the similarity between each keyword and its nearest neighbors in the embedding space. Finally, CLIME updates the embeddings using the annotations. We experiment clime on a cross-lingual text classification benchmark for four low-resource languages: Ilocano, Sinhalese, Tigrinya, and Uyghur. Embeddings refined by CLIME capture more nuanced word semantics and have higher test accuracy than the original embeddings. CLIME also improves test accuracy faster than an active learning baseline, and a simple combination of CLIME with active learning has the highest test accuracy.